MiniMax multimodal video

MiniMax H3

Generate 4–15 second video at 768P or 2K from text, first and last frames, or image, video, and audio references.

Examples

See what MiniMax H3 can make

What to create with MiniMax H3

Narrative shots

Control how a scene begins, develops, and lands on its final composition.

Character consistency

Use reference images to guide recurring subjects and visual identity.

Audiovisual concepts

Use video and audio references to shape motion, camera language, voice, and pace.

Why creators pick MiniMax H3

Start and end on your frames

Animate an opening image, land on a final image, or use both to define the arc of a shot while H3 builds the motion between them.

“The car revs through the desert.”

Direct with multimodal references

Assign images to character or style, video to motion or camera language, and audio to voice or editing rhythm. H3 accepts up to 9 images, 3 videos, and 3 audio clips.

Draft motion, then finish in 2K

Explore timing at 768P, then render the selected direction at 2K. Choose any duration from 4 to 15 seconds and see the credit estimate before generation.

Define the shot before H3 animates it

Boundary frames establish the composition, the prompt directs the action, and H3 creates the motion between them. This makes the generation path easier to understand before you spend credits.

1

Set the boundary frames

Upload a first frame, a last frame, or both to define where the shot begins and lands.

2

Describe the movement

Tell H3 what changes between the frames, including subject action, camera movement, timing, and sound.

3

Review the generated shot

H3 builds a continuous clip while preserving the intended opening and ending composition.

Series compare

Compare the MiniMax Hailuo series

Choose frontier multimodal control, high-fidelity generation with Recast/Relight/Lip Sync/Extend, or a faster production variant.

Frame rate
24 FPS
Duration
4–15 seconds
Resolution
768P or 2K
Audio
Native stereo
References
Image, video, audio
Compare the MiniMax Hailuo series
Feature
MiniMax H3Current
Best forMultimodal cinematic directionBudget drafts and high-volume generationEveryday video creationFast, reference-led productionMaximum-speed iterationMiniMax's video model for realistic human motion and expressive character performance.A faster Hailuo 2.3 variant for image animation and production iterations.Generate from text or animate an image with optional first and last frame control.A 512p Hailuo 02 variant for quick concepts and optional first and last frame guidance.
InputText, image, video, or audio referencesText, image, video, or audio referencesText, image, video, or audio referencesText, frames, multimodal references, or Recast source videoText or first and last framesText to video · Image to videoImage to videoText to video · Image to videoText to video · Image to video
Resolution768P or 2K768P or 480P768P480P, 768P, or 1080P480P, 768P, or 1080P768p / 1080p768p / 1080p512p / 768p / 1080p512p
Frame controlFirst and last framesFirst and last framesFirst and last framesFirst and last framesFirst and last framesFirst frameFirst frameFirst and last framesFirst and last frames
SpeedFlagshipBudget drafts and high-volume generationFaster generationFaster than real timeFastestStandardFastStandardFast

Tips for better results

1

Assign each reference a role

Explain whether a reference controls character, motion, camera, style, sound, or timing.

2

Use both boundary frames carefully

Choose compatible first and last frames, then describe the transition between them.

3

Prototype at 768P

Validate motion and composition at lower cost before generating the final 2K version.

MiniMax H3 — Frequently Asked Questions

Understand the inputs, generation settings, and outputs supported by MiniMax H3.

Related AI tools

Keep creating

View all tools

Create Videos with MiniMax H3